[All systems](https://mybb.ai/systems/)

# A project board *AI builds software from.*

Our own technology, in daily use: a project board that turns a backlog of tickets into tested, reviewed code, so our developers step in far less often.

Client

MYBB, for its own delivery

Industry

Software delivery

Connects to

Code repositories, the issue tracker and its test runs

## What we built

- The board
- The gate
- The cloud runner

The system, drawn with sample data. We never show a client’s own screens.

## 01 Overview

This is how we build. The board reads the plan, works out which tickets can be built side by side, and gives each one to an AI coding session in its own copy of the project. Every change is written test first, reviewed by a second AI from another vendor and proven before a person sees it.

01

### The board

A live page of every ticket, lane and session, and what each is waiting on.

02

### The gate

Runs only the tests a change can reach, and leaves a receipt for that exact change.

03

### The cloud runner

A private server per project that works unattended and asks its questions over WhatsApp.

## 02 The challenge

Every step waited for a developer.

AI models made writing code faster, but a developer still briefed each step, checked each answer and carried the work to the next one. Whatever was decided was lost between one session and the next.

### What the client wanted to achieve

#### Less human time

People are asked only for decisions.

#### Nothing unproven merges

A change merges only with passing proof for that exact change.

#### More work in parallel

Every safe ticket runs at once, the critical path first.

#### Works on any codebase

It attaches to a new project without rewriting the tool.

### How it worked before

- Instructions written again for every task
- Each answer checked by hand before the next step
- Decisions lost between sessions

**What we found**

After a combined change had passed all 13,867 of its tests, one model’s review still found six fixes and a second vendor’s review found five more. Each was fixed with a failing test first.

## 03 How we built it

1. 01 **A map of the work** It began as one screen of tickets and what blocks them, opening a workspace for each.
2. 02 **Proof before any merge** A local test gate that leaves a receipt bound to the exact change.
3. 03 **A second AI reviews** Reviews became structured findings judged by a model from another vendor, and a free slot starts the next ticket by itself.
4. 04 **Lanes that deliver alone** One command runs a whole line of tickets and delivers it once.
5. 05 **One tool, any project** It moved into its own home and learned to attach to any codebase from one settings file.
6. 06 **Plans by the critical path** It learns each project’s structure and plans the heaviest chain of work first.
7. 07 **Running without a laptop** Its own cloud server, an account that cannot merge on its own, and questions sent to people on their phones.

## 04 How it works

**How a ticket becomes tested code** Tickets run in parallel lanes and come back as reviewed code with its proof attached.

1. Step 01 **Plan** **Read the backlog** Tickets, blockers and priorities. **Pick what runs first** The heaviest chain first, in parallel lanes.
2. Step 02 **Build** **Test first** A failing test, then the code that passes it. **Isolated lanes** Each lane in its own copy, with its own data.
3. Step 03 **Review** **A second vendor** Another AI reviews the exact change, and every finding must point to real code.
4. Step 04 **Prove and merge** **Combined and proven** Finished lanes merged into one change and tested. **People on demand** Anything that needs a person reaches them on their phone.

### Before a person sees a change

- A new test that fails, then passes
- The existing tests the change can reach
- A review by a second vendor, bound to the exact change
- Every review finding grounded in the code
- One final run of everything the change touches
- A change to a guardrail still needs a person’s word

## 05 The outcome

We build with it every day. A backlog becomes tested, reviewed code ready to merge, and people step in only for the decisions that are theirs to make.

| Before | After |
| --- | --- |
| A developer briefing every step | Tickets that carry their own plan and rules |
| Answers checked by hand, one at a time | Tests run on every change before a person looks |
| One reviewer, or none | A second AI from another vendor reviews every change |
| Decisions lost between sessions | The project’s history on the board, for every next ticket |

## 06 Key figures

**230** tickets closed in 18 days

**13,867** tests passed in one full run of a combined change

**61** pull requests merged, each one proven first

**Tickets closed each week** Since the board moved into its own home.

Week 1 **39**

Week 2 **128**

Week 3 **63**

Week 3 counts its first three days.

## 07 Technology

What the system runs on, for the technical reader.

AI

Claude Code OpenAI Codex

Cloud

AWS WhatsApp for questions A daily email summary

Code and CI

Node.js GitHub Issues and pull requests GitHub Actions Isolated working copies Vitest

## 08 What comes next

Next, a whole batch of tickets delivered from its own server with nobody watching, its one real question asked over WhatsApp.

## 09 About

### About the client

Our own technology. We built the project board for our own delivery, and we develop it with the board itself, test first and reviewed twice.

### About MYBB

MYBB builds systems around how a business already works. We diagnose it with MYBB ROIQ, build the system, launch it with the team and keep running and improving it.

[All systems](https://mybb.ai/systems/)

## Questions about *our work.*

**Can you build something like this for my business?**

Each system here was built around one business. Answer the 10 questions, and within 48 hours your growth plan shows what we would build for yours.

**Why don’t you name the clients?**

We name a client only with their permission. Until then, each system is described by the kind of business it serves.

**Are these the real screens?**

They are redrawn with sample names and numbers. We never show a client’s own screens or data.

**My business is in a different industry. Does that matter?**

No. We start from how your business works, not from a template for its industry.

**Will we have to replace the tools we use?**

We start with what already works. The system may keep some of your tools, connect them, and add what’s missing.

**Who decides what the AI does?**

We agree with you where AI helps and where a person reviews, decides or approves. Those rules are part of the blueprint.

**Who runs the system once it’s built?**

We do, with your team. We keep running it and improving it as your business changes.

**How is the price set?**

By the scope, the connections and what the rollout needs. The price is in the blueprint, and nothing is built before you approve it.

[Software built with AI, ours first.](https://mybb.ai/start/)

We build our own software this way every day, and the same practice goes into every system we deliver. Tell us what you need built.

[Start with MYBB ROIQ](https://mybb.ai/start/)

Prefer to talk first? Email [welcome@mybb.ai](mailto:welcome@mybb.ai)

---

Source: [MYBB, for its own delivery | Our work | MYBB](https://mybb.ai/systems/project-board/)
